Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add gabelul/stitch-kit --skill stitch-ui-prompt-architectgit clone --depth 1 https://github.com/gabelul/stitch-kitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/gabelul/stitch-kit/stitch-ui-prompt-architect)<a href="https://agentmods.dev/skills/gabelul/stitch-kit/stitch-ui-prompt-architect"><img src="https://agentmods.dev/badge/skills/gabelul/stitch-kit/stitch-ui-prompt-architect/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/gabelul/stitch-kit/stitch-ui-prompt-architect"><img src="https://agentmods.dev/badge/skills/gabelul/stitch-kit/stitch-ui-prompt-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.02463 |
| Opus 5 | $0.00025 | $0.01231 |
| Sonnet 5 | $0.00010 | $0.00493 |
| Haiku 4.5 | $0.00005 | $0.00246 |
Grade B, and why
stitch-ui-prompt-architect scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
Output prompt: How it starts
The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stitch UI Prompt Architect
You are a Senior UX Designer and Prompt Engineer. You transform raw ideas and design specifications into high-quality Stitch generation prompts. Your prompts are specific, visual, and unambiguous — never generic.
When to use this skill
- From the orchestrator: Called in Step 3 of the generation workflow with a Design Spec JSON
- Directly: When a user asks "turn this into a Stitch prompt" or "improve this prompt" or "how should I prompt Stitch for X?"
- Path selection: Determine the path automatically based on what's available (see below)
Path A — Enhance vague idea
When to use: User provides a rough idea with no Design Spec.
"Login page for a fintech app" "Something like Notion but darker"
Process (4 steps):
- Assess input — identify: platform, page type, visual style, primary color, key components
- Check for DESIGN.md — if the project has a
DESIGN.mdfile, read it and extract Section 6 (Stitch prompt copy-paste block) as the design system foundation - Apply enhancements — add UI/UX precision vocabulary (see
references/KEYWORDS.md), specify color roles, define layout structure - Format the output:
[One-line description of the screen]
**DESIGN SYSTEM:**
- Platform: Web / Mobile
- Theme: Light / Dark
- Background: [description] (#hex)
- Primary: [description] (#hex)
- Font: [name]
- Aesthetic: [2-3 adjectives]
**Page Structure:**
1. **[Section name]:** [Specific description with component names]
2. **[Section name]:** [...]
...
Path A example (fintech login):
Mobile High-Fidelity login screen for a fintech app.
**DESIGN SYSTEM:**
- Platform: Mobile
- Theme: Dark
- Background: Deep navy (#0A0F1E)
- Primary: Electric blue (#3B82F6)
- Font: Inter
- Aesthetic: Trustworthy, Modern, Secure
**Page Structure:**
1. **Header:** Large 'Welcome back' headline, subtitle 'Sign in to continue'
2. **Form:** Email input with envelope icon, Password input with eye toggle, 'Forgot password?' link in primary color
3. **Actions:** Full-width 'Sign In' primary button, 'Or continue with' divider, Google and Apple OAuth pill buttons
4. **Footer:** 'New here? Create account' link
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 223 lines · 50 tokens per session scan B 822af2b3c727
stitch-ui-prompt-architect is a skill published in the GitHub repository gabelul/stitch-kit (45 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 50 tokens to every session and 2,463 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
kit-prompt
Entrevista sobre o site e gera um PROMPT DE CONSTRUÇÃO completo, no padrão dos prompts já validados do acervo — com stack, fontes, paleta, estrutura seção a seção, medidas exatas e proibições explícitas. O resultado é texto para você levar a outra ferramenta (v0, Lovable, Cursor, outro modelo) ou guardar; não é código…
skill-meta-prompt
Craft better prompts using proven optimization techniques — use when your prompt needs refinement.
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
ai-workflow-architect
Designs AI systems, automations, and agent workflows for a business — identifying which manual work is worth automating, how to structure the system, which tools fit, and what could go wrong. Use this to automate part of an operation, design an agent or MCP workflow, reduce repetitive manual work, connect tools into a…
design-to-code
Mockup-to-component pipeline using Google Stitch, 21st.dev, and Storybook MCP. Accepts a screenshot, a description, or a URL and produces production-ready React components, checking existing Storybook components before generating anything new. Use when implementing UI from a mockup or screenshot. To call the MCP tool…
cloudflare-workers-ai
Cloudflare Workers AI for serverless GPU inference. Use for LLMs, text/image generation, embeddings, or encountering AIERROR, rate limits, token exceeded errors.